Multiclass Classification for Meteorological Data using Modified CBS Algorithm with Multiple Minimum Support

• Published in: Indian journal of science and technology Vol. 8; no. 12; p. 1
• Main Authors: Astuti, Hanim Maria, Iqbal, Mohammad, Mukhlash, Imam
• Format: Journal Article
• Language: English
• Published: 01.06.2015
• Subjects: Algorithms; Categories; Classification; Climatology; Computer simulation; Performance enhancement; Weather; Weather forecasting
• ISSN: 0974-6846; 0974-5645; 0974-5645
• DOI: 10.17485/ijst/2015/v8i12/70652

Weather forecast is one of focuses in data mining which uses meteorological data for its process. As the common technique used in forecasting weather is sequential pattern, several algorithms have been developed by scholars. The common algorithms used in forecasting weather are: CBS algorithm, CBS algorithm using FEAT and CBS algorithm using FSGP. Previous studies remark the weaknesses of these three algorithms especially related to classifying weather with more than one class. In this paper, we use multiple minimum supports to modify CBS algorithm in order to improve the performance of weather forecasting. The result shows that making use multiple minimum supports to the three algorithms, the three modified algorithms are able to classify the weather with six categories from a given minimum support. In addition, the simulation result shows that the covacc parameter of the modified CBS algorithm is better than the three common algorithms.